{"id":25511296,"url":"https://github.com/yash-rewalia/introductory_qna_system","last_synced_at":"2026-02-12T21:31:41.423Z","repository":{"id":278124200,"uuid":"933828833","full_name":"yash-rewalia/Introductory_QnA_System","owner":"yash-rewalia","description":"This project is a Question-and-Answer (QnA) system that allows users to extract information from documents using semantic search and vector embeddings. The system processes documents, converts their content into embeddings, stores them in a knowledge base, and retrieves relevant answers based on user queries. ","archived":false,"fork":false,"pushed_at":"2025-02-18T05:06:20.000Z","size":42,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-02-18T06:22:25.790Z","etag":null,"topics":["gemini-api","generative-ai","llama-index","python","streamlit"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/yash-rewalia.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2025-02-16T19:25:24.000Z","updated_at":"2025-02-18T05:08:40.000Z","dependencies_parsed_at":"2025-02-18T06:22:32.545Z","dependency_job_id":"4bd41d09-1ae5-473e-8b6d-83be8bc14862","html_url":"https://github.com/yash-rewalia/Introductory_QnA_System","commit_stats":null,"previous_names":["yash-rewalia/introductory_qa_system"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yash-rewalia%2FIntroductory_QnA_System","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yash-rewalia%2FIntroductory_QnA_System/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yash-rewalia%2FIntroductory_QnA_System/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yash-rewalia%2FIntroductory_QnA_System/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/yash-rewalia","download_url":"https://codeload.github.com/yash-rewalia/Introductory_QnA_System/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":239640328,"owners_count":19673002,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["gemini-api","generative-ai","llama-index","python","streamlit"],"created_at":"2025-02-19T10:31:44.677Z","updated_at":"2026-02-12T21:31:41.391Z","avatar_url":"https://github.com/yash-rewalia.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Document-Based QnA System using LlamaIndex\n\n## Introduction\n\nThis project is a Question-and-Answer (QnA) system that allows users to extract information from documents using semantic search and vector embeddings. The system processes documents, converts their content into embeddings, stores them in a knowledge base, and retrieves relevant answers based on user queries. \n\n## Project Workflow\n\nBelow is the step-by-step process of how this system works:\n\n![NoteGPT-Flowchart-1739817148268](https://github.com/user-attachments/assets/178313dc-af39-478c-8435-d7e2475afbf8)\n8.png)\n\n1. **Document Input**: A document is provided for data extraction.\n2. **Data Extraction \u0026 Chunking**: The document is processed, and its content is split into smaller chunks.\n3. **Vector Embedding Generation**: Each chunk is converted into a vector embedding.\n4. **Semantic Indexing**: A semantic index is built using LlamaIndex.\n5. **Storage**: The embeddings are stored in a knowledge base or vector storage.\n6. **User Query**: A user submits a question.\n7. **Query Embedding Generation**: The query is transformed into an embedding.\n8. **Semantic Search**: The system performs a semantic search in the knowledge base.\n9. **Best Match Selection**: The most relevant answer is identified.\n10. **Response**: The answer is returned to the user.\n\n## Technologies Used\n\n- **LlamaIndex**: For building the semantic index.\n- **Vector Embeddings**: Used for document and query representation.\n- **Semantic Search**: To retrieve the most relevant answers.\n\n## Usage\n\n1. Upload a document.\n2. Ask a question related to the document.\n3. Receive the best possible answer based on the content.\n\n## Conclusion\n\nThis system enables efficient information retrieval from documents using AI-powered search techniques. Happy querying!\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyash-rewalia%2Fintroductory_qna_system","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fyash-rewalia%2Fintroductory_qna_system","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyash-rewalia%2Fintroductory_qna_system/lists"}